设为首页收藏本站
切换到宽版

Discuz!官方免费开源建站系统

 找回密码
 立即注册

QQ登录

只需一步，快速开始

搜索
Discuz!官方免费开源建站系统»论坛 › Discuz! 交流与讨论 › Discuz!-安装使用 › Discuz 使用sphinx实现全文搜索
返回列表 发新帖

[已解决] Discuz 使用sphinx实现全文搜索

[复制链接]
lishiming 发表于 2013-12-19 18:05:42 | 显示全部楼层 |阅读模式
原文： http://www.lishiming.net/thread-6514-1-1.html

centos系统上搭建sphinx，安装过程如下：

1.   安装软件
wget  http://www.coreseek.cn/uploads/csft/3.2/coreseek-3.2.13.tar.gz  
tar zxvf coreseek-3.2.13.tar.gz
cd coreseek-3.2.13
cd mmseg-3.2.13
./bootstrap   #这一步也许会出错，提示很多command not found ,  解决办法：  安装 libtool   centos 直接使用yum安装 : yum install -y libtool
./configure --prefix=/usr/local/mmseg
make  && make install
cd csft-3.2.13
./configure --prefix=/usr/local/sphinx  --with-mysql=/usr/local/mysql  --with-mmseg=/usr/local/mmseg/ --with-mmseg-includes=/usr/local/mmseg/include/mmseg/  --with-mmseg-libs=/usr/local/mmseg/lib/
make  && make install

2.  配置sphinx
vim /usr/local/sphinx/etc/csft.cnf  # 内容如下
  1. source threads
  2. {
  3.     type                    = mysql

  5.     sql_host                = localhost
  6.     sql_user                = user
  7.     sql_pass                = www.lishiming.net
  8.     sql_db                    = dbname
  9.     sql_port                = 3306
  10.     sql_query_pre            = SET NAMES gbk     #(这里如果数据库是GBK的就修改为gbk，下面所有SET NAME设置同这里)
  11.     sql_query_pre           = SET SESSION query_cache_type=OFF
  12.     sql_query_pre           = CREATE TABLE IF NOT EXISTS sph_counter ( counter_id INTEGER PRIMARY KEY NOT NULL,max_doc_id INTEGER NOT NULL)
  13.     sql_query_pre            = REPLACE INTO sph_counter SELECT 1, MAX(tid)-10 FROM pre_forum_thread

  15.     sql_query                = SELECT t.tid AS id,t.tid,t.subject,t.digest,t.displayorder,t.authorid,t.lastpost,t.special \
  16.                                 FROM pre_forum_thread AS t \
  17.                                 WHERE t.tid>=$start AND t.tid<=$end

  19.     sql_query_range            = SELECT (SELECT MIN(tid) FROM pre_forum_thread),max_doc_id FROM sph_counter WHERE counter_id=1
  20.     sql_range_step          = 4096

  22.     sql_attr_uint            = tid
  23.     sql_attr_uint            = digest
  24.     sql_attr_uint            = displayorder
  25.     sql_attr_uint            = authorid
  26.     sql_attr_uint            = special

  28.     sql_attr_timestamp        =lastpost

  30.     sql_query_info            = SELECT * FROM pre_forum_thread WHERE tid=$id
  31. }

  33. #threads
  34. index threads
  35. {
  36.     source            = threads
  37.     path            = /usr/local/sphinx/var/data/threads #windows下最好用全路径
  38.     docinfo            = extern
  39.     mlock            = 0
  40.     morphology        = none
  41.     charset_dictpath = /usr/local/mmseg/dict/    #BSD、Linux环境下设置，/符号结尾
  42.     #charset_debug   =   0
  43. #### 索引的词最小长度
  44. min_word_len = 1
  45. #charset_type =
  46. html_strip = 0

  48. ##### 字符表，注意：如使用这种方式，则sphinx会对中文进行单字切分，
  49. ##### 即进行字索引，若要使用中文分词，必须使用其他分词插件如 coreseek，sfc
  50. charset_table = U+FF10..U+FF19->0..9, 0..9, U+FF41..U+FF5A->a..z, U+FF21..U+FF3A->a..z,\
  51. A..Z->a..z, a..z, U+0149, U+017F, U+0138, U+00DF, U+00FF, U+00C0..U+00D6->U+00E0..U+00F6,\
  52. U+00E0..U+00F6, U+00D8..U+00DE->U+00F8..U+00FE, U+00F8..U+00FE, U+0100->U+0101, U+0101,\
  53. U+0102->U+0103, U+0103, U+0104->U+0105, U+0105, U+0106->U+0107, U+0107, U+0108->U+0109,\
  54. U+0109, U+010A->U+010B, U+010B, U+010C->U+010D, U+010D, U+010E->U+010F, U+010F,\
  55. U+0110->U+0111, U+0111, U+0112->U+0113, U+0113, U+0114->U+0115, U+0115, \
  56. U+0116->U+0117,U+0117, U+0118->U+0119, U+0119, U+011A->U+011B, U+011B, U+011C->U+011D,\
  57. U+011D,U+011E->U+011F, U+011F, U+0130->U+0131, U+0131, U+0132->U+0133, U+0133, \
  58. U+0134->U+0135,U+0135, U+0136->U+0137, U+0137, U+0139->U+013A, U+013A, U+013B->U+013C, \
  59. U+013C,U+013D->U+013E, U+013E, U+013F->U+0140, U+0140, U+0141->U+0142, U+0142, \
  60. U+0143->U+0144,U+0144, U+0145->U+0146, U+0146, U+0147->U+0148, U+0148, U+014A->U+014B, \
  61. U+014B,U+014C->U+014D, U+014D, U+014E->U+014F, U+014F, U+0150->U+0151, U+0151, \
  62. U+0152->U+0153,U+0153, U+0154->U+0155, U+0155, U+0156->U+0157, U+0157, U+0158->U+0159,\
  63. U+0159,U+015A->U+015B, U+015B, U+015C->U+015D, U+015D, U+015E->U+015F, U+015F, \
  64. U+0160->U+0161,U+0161, U+0162->U+0163, U+0163, U+0164->U+0165, U+0165, U+0166->U+0167, \
  65. U+0167,U+0168->U+0169, U+0169, U+016A->U+016B, U+016B, U+016C->U+016D, U+016D, \
  66. U+016E->U+016F,U+016F, U+0170->U+0171, U+0171, U+0172->U+0173, U+0173, U+0174->U+0175,\
  67. U+0175,U+0176->U+0177, U+0177, U+0178->U+00FF, U+00FF, U+0179->U+017A, U+017A, \
  68. U+017B->U+017C,U+017C, U+017D->U+017E, U+017E, U+0410..U+042F->U+0430..U+044F, \
  69. U+0430..U+044F,U+05D0..U+05EA, U+0531..U+0556->U+0561..U+0586, U+0561..U+0587, \
  70. U+0621..U+063A, U+01B9,U+01BF, U+0640..U+064A, U+0660..U+0669, U+066E, U+066F, \
  71. U+0671..U+06D3, U+06F0..U+06FF,U+0904..U+0939, U+0958..U+095F, U+0960..U+0963, \
  72. U+0966..U+096F, U+097B..U+097F,U+0985..U+09B9, U+09CE, U+09DC..U+09E3, U+09E6..U+09EF, \
  73. U+0A05..U+0A39, U+0A59..U+0A5E,U+0A66..U+0A6F, U+0A85..U+0AB9, U+0AE0..U+0AE3, \
  74. U+0AE6..U+0AEF, U+0B05..U+0B39,U+0B5C..U+0B61, U+0B66..U+0B6F, U+0B71, U+0B85..U+0BB9, \
  75. U+0BE6..U+0BF2, U+0C05..U+0C39,U+0C66..U+0C6F, U+0C85..U+0CB9, U+0CDE..U+0CE3, \
  76. U+0CE6..U+0CEF, U+0D05..U+0D39, U+0D60,U+0D61, U+0D66..U+0D6F, U+0D85..U+0DC6, \
  77. U+1900..U+1938, U+1946..U+194F, U+A800..U+A805,U+A807..U+A822, U+0386->U+03B1, \
  78. U+03AC->U+03B1, U+0388->U+03B5, U+03AD->U+03B5,U+0389->U+03B7, U+03AE->U+03B7, \
  79. U+038A->U+03B9, U+0390->U+03B9, U+03AA->U+03B9,U+03AF->U+03B9, U+03CA->U+03B9, \
  80. U+038C->U+03BF, U+03CC->U+03BF, U+038E->U+03C5,U+03AB->U+03C5, U+03B0->U+03C5, \
  81. U+03CB->U+03C5, U+03CD->U+03C5, U+038F->U+03C9,U+03CE->U+03C9, U+03C2->U+03C3, \
  82. U+0391..U+03A1->U+03B1..U+03C1,U+03A3..U+03A9->U+03C3..U+03C9, U+03B1..U+03C1, \
  83. U+03C3..U+03C9, U+0E01..U+0E2E,U+0E30..U+0E3A, U+0E40..U+0E45, U+0E47, U+0E50..U+0E59, \
  84. U+A000..U+A48F, U+4E00..U+9FBF,U+3400..U+4DBF, U+20000..U+2A6DF, U+F900..U+FAFF, \
  85. U+2F800..U+2FA1F, U+2E80..U+2EFF,U+2F00..U+2FDF, U+3100..U+312F, U+31A0..U+31BF, \
  86. U+3040..U+309F, U+30A0..U+30FF,U+31F0..U+31FF, U+AC00..U+D7AF, U+1100..U+11FF, \
  87. U+3130..U+318F, U+A000..U+A48F,U+A490..U+A4CF
  88. min_prefix_len = 0
  89. min_infix_len = 1
  90. ngram_len = 1
  91. }

  93. #threads_minute
  94. source threads_minute : threads
  95. {
  96.     sql_query_pre            =
  97.     sql_query_pre            = SET NAMES gbk
  98.     sql_query_pre           = SET SESSION query_cache_type=OFF

  100.     sql_query_range            = SELECT max_doc_id+1,(SELECT MAX(tid) FROM pre_forum_thread) FROM sph_counter WHERE counter_id=1
  101. }

  103. #threads_minute
  104. index threads_minute : threads
  105. {
  106.     source            = threads_minute
  107.     path            = /usr/local/sphinx/var/data/threads_minute #windows下最好用全路径
  108. }

  110. ##################################################

  112. #posts
  113. source posts
  114. {
  115.     type                    = mysql

  117.     sql_host                = localhost
  118.     sql_user                = user
  119.     sql_pass                = www.lishiming.net
  120.     sql_db                    = dbname
  121.     sql_port                = 3306
  122.     sql_query_pre            =
  123.     sql_query_pre            = SET NAMES gbk
  124.     sql_query_pre           = SET SESSION query_cache_type=OFF
  125.     sql_query_pre           = CREATE TABLE IF NOT EXISTS sph_counter ( counter_id INTEGER PRIMARY KEY NOT NULL,max_doc_id INTEGER NOT NULL)
  126.     sql_query_pre            = REPLACE INTO sph_counter SELECT 2, MAX(pid)-2 FROM pre_forum_post

  128.     sql_query                = SELECT p.pid AS id,p.tid,p.subject,p.message,t.digest,t.displayorder,t.authorid,t.lastpost,t.special \
  129.                                 FROM pre_forum_post AS p LEFT JOIN pre_forum_thread AS t USING(tid) \
  130.                                 WHERE p.pid>=$start AND p.pid<=$end

  132.     sql_query_range            = SELECT (SELECT MIN(pid) FROM pre_forum_post),max_doc_id FROM sph_counter WHERE counter_id=2
  133.     sql_range_step          = 4096

  135.     sql_attr_uint            = tid
  136.     sql_attr_uint            = digest
  137.     sql_attr_uint            = displayorder
  138.     sql_attr_uint            = authorid
  139.     sql_attr_uint            = special

  141.     sql_attr_timestamp        =lastpost

  143.     sql_query_info            = SELECT * FROM pre_forum_post WHERE pid=$id
  144. }

  146. #posts
  147. index posts
  148. {
  149.     source            = posts
  150.     path            = /usr/local/sphinx/var/data/posts #windows下最好用全路径
  151.     docinfo            = extern
  152.     mlock            = 0
  153.     morphology        = none
  154.     charset_dictpath = /usr/local/mmseg/dict/    #BSD、Linux环境下设置，/符号结尾
  155.     #charset_debug   =   0
  156. #### 索引的词最小长度
  157. min_word_len = 1
  158. #charset_type =
  159. html_strip = 0

  161. ##### 字符表，注意：如使用这种方式，则sphinx会对中文进行单字切分，
  162. ##### 即进行字索引，若要使用中文分词，必须使用其他分词插件如 coreseek，sfc
  163. charset_table = U+FF10..U+FF19->0..9, 0..9, U+FF41..U+FF5A->a..z, U+FF21..U+FF3A->a..z,\
  164. A..Z->a..z, a..z, U+0149, U+017F, U+0138, U+00DF, U+00FF, U+00C0..U+00D6->U+00E0..U+00F6,\
  165. U+00E0..U+00F6, U+00D8..U+00DE->U+00F8..U+00FE, U+00F8..U+00FE, U+0100->U+0101, U+0101,\
  166. U+0102->U+0103, U+0103, U+0104->U+0105, U+0105, U+0106->U+0107, U+0107, U+0108->U+0109,\
  167. U+0109, U+010A->U+010B, U+010B, U+010C->U+010D, U+010D, U+010E->U+010F, U+010F,\
  168. U+0110->U+0111, U+0111, U+0112->U+0113, U+0113, U+0114->U+0115, U+0115, \
  169. U+0116->U+0117,U+0117, U+0118->U+0119, U+0119, U+011A->U+011B, U+011B, U+011C->U+011D,\
  170. U+011D,U+011E->U+011F, U+011F, U+0130->U+0131, U+0131, U+0132->U+0133, U+0133, \
  171. U+0134->U+0135,U+0135, U+0136->U+0137, U+0137, U+0139->U+013A, U+013A, U+013B->U+013C, \
  172. U+013C,U+013D->U+013E, U+013E, U+013F->U+0140, U+0140, U+0141->U+0142, U+0142, \
  173. U+0143->U+0144,U+0144, U+0145->U+0146, U+0146, U+0147->U+0148, U+0148, U+014A->U+014B, \
  174. U+014B,U+014C->U+014D, U+014D, U+014E->U+014F, U+014F, U+0150->U+0151, U+0151, \
  175. U+0152->U+0153,U+0153, U+0154->U+0155, U+0155, U+0156->U+0157, U+0157, U+0158->U+0159,\
  176. U+0159,U+015A->U+015B, U+015B, U+015C->U+015D, U+015D, U+015E->U+015F, U+015F, \
  177. U+0160->U+0161,U+0161, U+0162->U+0163, U+0163, U+0164->U+0165, U+0165, U+0166->U+0167, \
  178. U+0167,U+0168->U+0169, U+0169, U+016A->U+016B, U+016B, U+016C->U+016D, U+016D, \
  179. U+016E->U+016F,U+016F, U+0170->U+0171, U+0171, U+0172->U+0173, U+0173, U+0174->U+0175,\
  180. U+0175,U+0176->U+0177, U+0177, U+0178->U+00FF, U+00FF, U+0179->U+017A, U+017A, \
  181. U+017B->U+017C,U+017C, U+017D->U+017E, U+017E, U+0410..U+042F->U+0430..U+044F, \
  182. U+0430..U+044F,U+05D0..U+05EA, U+0531..U+0556->U+0561..U+0586, U+0561..U+0587, \
  183. U+0621..U+063A, U+01B9,U+01BF, U+0640..U+064A, U+0660..U+0669, U+066E, U+066F, \
  184. U+0671..U+06D3, U+06F0..U+06FF,U+0904..U+0939, U+0958..U+095F, U+0960..U+0963, \
  185. U+0966..U+096F, U+097B..U+097F,U+0985..U+09B9, U+09CE, U+09DC..U+09E3, U+09E6..U+09EF, \
  186. U+0A05..U+0A39, U+0A59..U+0A5E,U+0A66..U+0A6F, U+0A85..U+0AB9, U+0AE0..U+0AE3, \
  187. U+0AE6..U+0AEF, U+0B05..U+0B39,U+0B5C..U+0B61, U+0B66..U+0B6F, U+0B71, U+0B85..U+0BB9, \
  188. U+0BE6..U+0BF2, U+0C05..U+0C39,U+0C66..U+0C6F, U+0C85..U+0CB9, U+0CDE..U+0CE3, \
  189. U+0CE6..U+0CEF, U+0D05..U+0D39, U+0D60,U+0D61, U+0D66..U+0D6F, U+0D85..U+0DC6, \
  190. U+1900..U+1938, U+1946..U+194F, U+A800..U+A805,U+A807..U+A822, U+0386->U+03B1, \
  191. U+03AC->U+03B1, U+0388->U+03B5, U+03AD->U+03B5,U+0389->U+03B7, U+03AE->U+03B7, \
  192. U+038A->U+03B9, U+0390->U+03B9, U+03AA->U+03B9,U+03AF->U+03B9, U+03CA->U+03B9, \
  193. U+038C->U+03BF, U+03CC->U+03BF, U+038E->U+03C5,U+03AB->U+03C5, U+03B0->U+03C5, \
  194. U+03CB->U+03C5, U+03CD->U+03C5, U+038F->U+03C9,U+03CE->U+03C9, U+03C2->U+03C3, \
  195. U+0391..U+03A1->U+03B1..U+03C1,U+03A3..U+03A9->U+03C3..U+03C9, U+03B1..U+03C1, \
  196. U+03C3..U+03C9, U+0E01..U+0E2E,U+0E30..U+0E3A, U+0E40..U+0E45, U+0E47, U+0E50..U+0E59, \
  197. U+A000..U+A48F, U+4E00..U+9FBF,U+3400..U+4DBF, U+20000..U+2A6DF, U+F900..U+FAFF, \
  198. U+2F800..U+2FA1F, U+2E80..U+2EFF,U+2F00..U+2FDF, U+3100..U+312F, U+31A0..U+31BF, \
  199. U+3040..U+309F, U+30A0..U+30FF,U+31F0..U+31FF, U+AC00..U+D7AF, U+1100..U+11FF, \
  200. U+3130..U+318F, U+A000..U+A48F,U+A490..U+A4CF
  201. min_prefix_len = 0
  202. min_infix_len = 1
  203. ngram_len = 1
  204. }

  206. #posts_minute
  207. source posts_minute : posts
  208. {
  209.     sql_query_pre            =
  210.     sql_query_pre            = SET NAMES gbk
  211.     sql_query_pre           = SET SESSION query_cache_type=OFF

  213.     sql_query_range            = SELECT max_doc_id+1,(SELECT MAX(pid) FROM pre_forum_post) FROM sph_counter WHERE counter_id=2
  214. }

  216. #posts_minute
  217. index posts_minute : posts
  218. {
  219.     source            = posts_minute
  220.     path            = /usr/local/sphinx/var/data/posts_minute #windows下最好用全路径
  221. }

  223. #全局indexer定义
  224. indexer
  225. {
  226.     mem_limit            = 256M
  227. }

  229. #searchd服务定义
  230. searchd
  231. {
  232.     listen              = 3312
  233.     read_timeout        = 5
  234.     max_children        = 30
  235.     max_matches            = 10000
  236.     seamless_rotate        = 0
  237.     preopen_indexes        = 0
  238.     unlink_old            = 1
  239.     pid_file            = /usr/local/sphinx/var/log/searchd_discuzx.pid #windows下最好用全路径
  240.     log                 = /usr/local/sphinx/var/log/searchd_discuzx.log #windows下最好用全路径
  241.     query_log           = /usr/local/sphinx/var/log/query_discuzx.log #windows下最好用全路径
  242. }
复制代码


3. 首次生成索引
/usr/local/sphinx/bin/indexer --config  /usr/local/sphinx/etc/csft.conf --all

4. 启动sphinx
/usr/local/sphinx/bin/searchd --config  /usr/local/sphinx/etc/csft.conf

5. 指定计划任务
  1. * 0-3 * * * root /usr/local/sphinx/bin/indexer --config  /usr/local/sphinx/etc/csft.conf posts_minute --rotate
  2. * 6-23 * * * root /usr/local/sphinx/bin/indexer --config  /usr/local/sphinx/etc/csft.conf posts_minute --rotate
  3. 0 4 * * * root /usr/local/sphinx/bin/indexer --config  /usr/local/sphinx/etc/csft.conf posts_merge --rotate && /usr/local/sphinx/bin/indexer --config  /usr/local/sphinx/etc/csft.conf --merge posts posts_merge --rotate  

  5. * 0-3 * * * root /usr/local/sphinx/bin/indexer --config  /usr/local/sphinx/etc/csft.conf threads_minute --rotate  
  6. * 6-23 * * * root /usr/local/sphinx/bin/indexer --config  /usr/local/sphinx/etc/csft.conf threads_minute --rotate  
  7. 0 4 * * * root /usr/local/sphinx/bin/indexer --config  /usr/local/sphinx/etc/csft.conf threads_merge --rotate && /usr/local/sphinx/bin/indexer --config  /usr/local/sphinx/etc/csft.conf --merge threads threads_merge --rotate
复制代码


6. 设置discuz后台
使用创始人账号登陆discuz后台， 全局 -> 搜索设置 ->  
开启sphinx
sphinx 主机名  localhost
端口： 3312
标题索引名： threads,threads_minute
全文索引名：posts,posts_minute
项目数：10000
模式：保持默认即可

7. 更改discuz代码
打开/source/module/search/forum.php  
找到以下这行  
if($srchtype == 'fulltext' && $_G['setting']['sphinxon']) {
改成   
if($_G['setting']['sphinxon']) {
再找到下面几行（注意：仅在你discuz版本为gbk时才需要做 以下修改）   
f($srchtype == "fulltext") {   
$result = $s->query("'".$srchtxt."'",  $_G['setting']['sphinxmsgindex']);  
} else {  
$result = $s->query($srchtxt,  $_G['setting']['sphinxsubindex']);  
}  
改成  
$_srchtxt = iconv('gbk','utf-8',$srchtxt); //将gbk转成 utf-8   
if($srchtype == "fulltext") {   
$result = $s->query("'".$_srchtxt."'",  $_G['setting']['sphinxmsgindex']);  
} else {   
$result = $s->query($_srchtxt,  $_G['setting']['sphinxsubindex']);  
}   

结束
回复

使用道具 举报

ＫiＳsゞ 发表于 2013-12-19 19:12:38 | 显示全部楼层
{:soso_e134:}直接晕了
回复

使用道具 举报

crx349 发表于 2014-2-27 15:13:13 | 显示全部楼层
方案还是有缺陷~中文不是太准 哎。。。
回复

使用道具 举报

劣狼 发表于 2021-4-7 20:14:07 | 显示全部楼层
Mark
标记一下
回复

使用道具 举报

返回列表 发新帖
高级模式
B Color Image Link Quote Code Smilies
您需要登录后才可以回帖 登录 | 立即注册

本版积分规则

手机版|小黑屋|Discuz! 官方站 ( 皖ICP备16010102号 )star

GMT+8, 2024-11-23 19:33 , Processed in 0.024955 second(s), 4 queries , Gzip On, Redis On.

Powered by Discuz! X3.4

Copyright © 2001-2023, Tencent Cloud.

快速回复 返回顶部 返回列表